按年被提到
20202020 · 2 次2026
机器学习与深度学习›机器学习实践与反思·arXiv:2004.07780 · cs.CV

Shortcut Learning in Deep Neural Networks

Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, Felix A. Wichmann · 2020
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2020-04-18 · 最近 2020-06-10
2不同的人
2活跃月份
2讨论串
2,309被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distill how many of deep learning's problems can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论ArtWomb · 2020-06

“Humans observe an object once, such as a cup for drinking water, and we immediately grasp its "cupness". We can identify infinite varieties of cups despite variations in morphology, design, utility and context. Simply based on a single learning instance. This absence of any neural theory of inference is at the crux of the problem;) Shortcut Learning in …”

Stanford Class on Deep Multi-Task and Meta-Learning原评论 ↗
被提交为 story · 1 次